With the recent advancements in wearables and sensing technology, health scientists are increasingly developing mobile health (mHealth) interventions. In mHealth interventions, mobile devices are used to deliver treatment to individuals as they go about their daily lives, generally designed to impact a near time, proximal outcome such as stress or physical activity. The mHealth intervention policies, often called Just-In-time Adaptive Interventions, are decision rules that map a user's context to a particular treatment at each of many time points. The vast majority of current mHealth interventions deploy expert-derived policies. In this paper, we provide an approach for conducting inference about the performance of one or more such policies. In particular, we estimate the performance of a mHealth policy using historical data that are collected under a possibly different policy. Our measure of performance is the average of proximal outcomes (rewards) over a long time period should the particular mHealth policy be followed. We provide a semi-parametric efficient estimator as well as the confidence intervals. This work is motivated by HeartSteps, a mobile health physical activity intervention.

本文探讨了移动健康干预技术(mHealth)中的即时自适应干预政策，包括专家提供的政策以及基于历史数据的干预政策效果估计，并提供了一个估计器和置信区间，以评估这类政策在长期内是否能提高健康结果。

应用于移动健康的长期平均结果的离策略估计